© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 73302
    Prev
    Next
    INDEX
    Explanations

    october dates

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron fires on numeric date/time expressions (e.g. months, years, and other numeric tokens in timestamp‐style contexts).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     April
    -2.30
    April
    -2.22
     Easter
    -2.11
     APRIL
    -2.08
    Easter
    -2.06
    June
    -2.00
     June
    -2.00
    APRIL
    -1.98
     March
    -1.95
    april
    -1.92
    POSITIVE LOGITS
     October
    4.28
    October
    4.03
     Oct
    3.47
     Halloween
    3.41
     November
    3.30
     autumn
    3.30
     OCTOBER
    3.22
    November
    3.17
     october
    3.14
     September
    3.09
    Activations Density 0.468%

    No Known Activations